INDEX

Explanations

phrases related to leaving or exiting

oai_token-act-pair · gpt-3.5-turbo

references to departures or exits from a situation or location

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flix

-0.71

ibur

-0.71

 Metatron

-0.70

iop

-0.69

Cola

-0.68

umen

-0.66

acher

-0.65

icum

-0.65

ested

-0.64

itness

-0.63

POSITIVE LOGITS

 from

0.99

 undone

0.82

 FROM

0.79

 From

0.72

from

0.71

owship

0.67

 away

0.67

 Leaves

0.66

 hither

0.66

doms

0.66

Activations Density 0.065%

phrases related to leaving or exiting

references to departures or exits from a situation or location

No Comments

No Known Activations